Compressive Sensing Based on HQS for Image reconstruction

Qinqin Tang, Mingwei Li, Yuming Zhang


This work solves the image distortion problem caused by the noise generated during the sampling and reconstruction
process, a compressive sensing algorithm based on half quadratic splitting (CS-HQS) is proposed to reconstruct images in this paper. For
the part dominated by error terms, the regularization term is introduced and the second-order momentum adaptive gradient descent method
is used to get the auxiliary variables. For the part dominated by the sparse prior of compressive sensing, the Bayesian maximum posterior
inference is used to get the sparse coeffi cient. The combination of the two methods not only avoids the generation of random noise, but also
enhances the stability of the model. The experimental results demonstrate that the strong robustness of the proposed algorithm.


Compressive sensing, Bayesian learning; Second-order momentum adaptive gradient descent; Image reconstruction

Full Text:


Included Database


[1] E. J. Candes and M. B. Wakin, “An Introduction To Compressive Sampling,” in IEEE Signal Processing Magazine, vol. 25, no. 2, pp. 21-30, March 2008,

doi: 10.1109/MSP.2007.914731.

[2] S. Ji, Y. Xue and L. Carin, “Bayesian Compressive Sensing,” in IEEE Transactions on Signal Processing, vol. 56, no. 6, pp. 2346-2356, June 2008, doi:


[3] Le Qin, Yuanlong Cao, Xun Shao, Yong Luo, Xinping Rao, Yugen Yi, Gang Lei,A deep heterogeneous optimization framework for Bayesian compressive

sensing,Computer Communications,Volume 178,2021,Pages 74-82,ISSN 0140-3664.

[4] Z. Chen et al., “Deep-Learned Regularization and Proximal Operator for Image Compressive Sensing,” in IEEE Transactions on Image Processing, vol.

30, pp. 7112-7126, 2021, doi: 10.1109/TIP.2021.3088611.

[5] Z. Zhou, K. Liu and J. Fang, “Bayesian Compressive Sensing Using Normal Product Priors,” in IEEE Signal Processing Letters, vol. 22, no. 5, pp. 583-

587, May 2015, doi: 10.1109/LSP.2014.2364255.

[6] Liu Le, Wang Hongguo and Wang Baowei, “A modifi ed BP network based on second order momentum term,” 2008 27th Chinese Control Conference,

2008, pp. 682-686, doi: 10.1109/CHICC.2008.4605423.

[7] Y. Li, F. Liu, L. Yu and Q. Qi, “Regression Model Based on Sparse Bayesian Learning,” 2010 International Conference on Artifi cial Intelligence and

Computational Intelligence, 2010, pp. 542-545, doi: 10.1109/AICI.2010.119.

[8] Q. Cheng, A. A. Ihalage, Y. Liu and Y. Hao, “Compressive Sensing Radar Imaging With Convolutional Neural Networks,” in IEEE Access, vol. 8, pp.

212917-212926, 2020, doi: 10.1109/ACCESS.2020.3040498.

[9] H. Palangi, R. Ward and L. Deng, “Distributed Compressive Sensing: A Deep Learning Approach,” in IEEE Transactions on Signal Processing, vol. 64,

no. 17, pp. 4504-4518, 1 Sept.1, 2016, doi: 10.1109/TSP.2016.2557301.

[10] L. Tang, Z. Zhou, L. Shi, H. Yao, J. Zhang and Y. Ye, “Laplace prior based distributed compressive sensing,” 2010 5th International ICST Conference on

Communications and Networking in China, 2010, pp. 1-4, doi: 10.4108/chinacom.2010.82.

[11] Z. Zhang, Y. Liu, J. Liu, F. Wen and C. Zhu, “AMP-Net: Denoising-Based Deep Unfolding for Compressive Image Sensing,” in IEEE Transactions on

Image Processing, vol. 30, pp. 1487-1500, 2021, doi: 10.1109/TIP.2020.3044472.



  • There are currently no refbacks.

Copyright (c) 2023 Qinqin Tang,Mingwei Li,Yuming Zhang